Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
Model details →NousResearch: Hermes 2 Pro - Llama-3 8B vs Sao10K: Llama 3 8B Lunaris
Sao10K: Llama 3 8B Lunaris wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge. Created by [Sao10k](https://huggingface.co/Sa…
Model details →Side-by-side comparison
| Capability | NousResearch: Hermes 2 Pro - Llama-3 8B | Sao10K: Llama 3 8B Lunaris | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 8K | 8K | Tie |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.14 | $0.04 | 🏆 Sao10K: Llama 3 8B Lunaris |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.14 | $0.05 | 🏆 Sao10K: Llama 3 8B Lunaris |
| Tool / function calling First-class support for emitting structured tool calls. | — | — | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is NousResearch: Hermes 2 Pro - Llama-3 8B better than Sao10K: Llama 3 8B Lunaris?
Sao10K: Llama 3 8B Lunaris wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between NousResearch: Hermes 2 Pro - Llama-3 8B and Sao10K: Llama 3 8B Lunaris?
Input: $0.14 vs $0.04 per 1M tokens. Output: $0.14 vs $0.05 per 1M tokens.
What context windows do NousResearch: Hermes 2 Pro - Llama-3 8B and Sao10K: Llama 3 8B Lunaris support?
NousResearch: Hermes 2 Pro - Llama-3 8B supports up to 8K tokens. Sao10K: Llama 3 8B Lunaris supports up to 8K tokens.
Do both NousResearch: Hermes 2 Pro - Llama-3 8B and Sao10K: Llama 3 8B Lunaris support tool calling?
NousResearch: Hermes 2 Pro - Llama-3 8B: not advertised. Sao10K: Llama 3 8B Lunaris: not advertised.